# Few-shot Training

TinyLLaVA-Video-R1 is a video-text-to-text model obtained through cold-start training of TinyLLaVA-Video using 16 manually annotated samples from the NextQA dataset.

R1-AQA is an audio question answering model based on Qwen2-Audio-7B-Instruct, optimized through Group Relative Policy Optimization (GRPO) algorithm, achieving state-of-the-art performance in the MMAU benchmark.

An image classification model based on the BEiT architecture, fine-tuned on the FER2013 dataset for facial expression recognition

This is a diffusion model initialized with Google's DDPM bedroom image model and fine-tuned on the WikiArt dataset for unconditional image generation.

An English text summarization generator fine-tuned on the BART model, trained on the CNN-DailyMail dataset